Skip to content

Grab dependencies automatically #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
narendasan opened this issue Mar 13, 2020 · 0 comments · Fixed by #48
Closed

Grab dependencies automatically #14

narendasan opened this issue Mar 13, 2020 · 0 comments · Fixed by #48
Labels
feature request New feature or request

Comments

@narendasan
Copy link
Collaborator

We should either look at containerizing the build, or find someway to pull TensorRT, CUDA etc. with bazel. We already do this with libtorch. This should make it less likely builds will fail because of peoples environment
@narendasan narendasan added the feature request New feature or request label Mar 13, 2020
narendasan added a commit that referenced this issue Apr 29, 2020
@narendasan
refactor: Upgrading to LibTorch 1.5.0 (CUDA 10.2, cuDNN 7.6.5, TensorRT
a51c7b6 
7.0.0)

- Closes #42
- Issue #1 is back, unknown root cause, will follow up with the PyTorch
Team
- Closes #14: The default build now requires users to grab the tarballs
from the NVIDIA website to support hermetic builds, may look at some
methods to smooth this out later. The old method is still available
- New operators need to be implemented to support MobileNet in 1.5.0
(blocks merge into master)

Signed-off-by: Naren Dasan <[email protected]>
Signed-off-by: Naren Dasan <[email protected]>
@narendasan narendasan mentioned this issue Apr 29, 2020
Merged
@zhanjw zhanjw mentioned this issue Jul 19, 2020
Closed
frank-wei pushed a commit that referenced this issue Jun 4, 2022
Add baddbmm operator support (#14)
159e77c 
Summary:
Pull Request resolved: https://github.com/pytorch/fx2trt/pull/14

Add support for torch.baddbmm. Add unit test to cover bmm and addmm, both are mapping to other converter insteand of having new acc_op converter.

Reviewed By: yinghai

Differential Revision: D34743279

fbshipit-source-id: efd417b2b494635c63f2ec58daa3fc568f72111a
@zewenli98 zewenli98 mentioned this issue Aug 13, 2024
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
feature request New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Upgrading to LibTorch 1.5.0 (CUDA 10.2, cuDNN 7.6.5, TensorRT 7.0.0) pytorch/TensorRT
1 participant
@narendasan